Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4701 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.9881. Min Act: -0.1700
Data Index: 6980817 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.9569. Min Act: -0.1700
Data Index: 6980811 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.8631. Min Act: -0.1700
Data Index: 2859836 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.8631. Min Act: -0.1700
Data Index: 7887330 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.8319. Min Act: -0.1700
Data Index: 2075524 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.7694. Min Act: -0.1700
Data Index: 622947 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.7694. Min Act: -0.1700
Data Index: 1169027 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.7381. Min Act: -0.1700
Data Index: 1490653 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.7069. Min Act: -0.1700
Data Index: 3587044 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.7069. Min Act: -0.1700
Data Index: 3678249 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.7069. Min Act: -0.1700
Data Index: 6980830 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.6756. Min Act: -0.1700
Data Index: 4951220 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.6444. Min Act: -0.1700
Data Index: 7661529 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.6756. Min Act: -0.1700
Data Index: 6980821 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.6756. Min Act: -0.1700
Data Index: 7887331 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.6444. Min Act: -0.1700
Data Index: 3541019 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.6444. Min Act: -0.1700
Data Index: 5377278 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.6444. Min Act: -0.1700
Data Index: 5717506 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.6444. Min Act: -0.1700
Data Index: 2154421 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.6444. Min Act: -0.1700
Data Index: 4955970 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #19